distilbert-base-uncased-finetuned-imdb-whole-word-masking

This model is a fine-tuned version of distilbert-base-uncased on the IMDB dataset. It achieves the following results on the evaluation set:

• Loss: 3.0554

Model description

The model is trained using whole word masking.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.2819	1.0	782	3.1161
3.2058	2.0	1564	3.0585
3.1674	3.0	2346	3.0554

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0